Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5469 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.2912. Min Range: -7.2912

Max Act: 6.9480. Min Act: -0.0000

Data Index: 404983 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 7.2912. Min Range: -7.2912

Max Act: 7.2912. Min Act: -0.0000

Data Index: 24407 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 7.2912. Min Range: -7.2912

Max Act: 6.8596. Min Act: -0.0000

Data Index: 663021 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 7.2912. Min Range: -7.2912

Max Act: 6.8476. Min Act: -0.0000

Data Index: 1031995 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 7.2912. Min Range: -7.2912

Max Act: 7.1657. Min Act: -0.0000

Data Index: 1047683 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 7.2912. Min Range: -7.2912

Max Act: 6.7763. Min Act: -0.0000

Data Index: 267928 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 7.2912. Min Range: -7.2912

Max Act: 5.9469. Min Act: -0.0000

Data Index: 1133202 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 7.2912. Min Range: -7.2912

Max Act: 6.4989. Min Act: -0.0000

Data Index: 398756 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 7.2912. Min Range: -7.2912

Max Act: 5.9167. Min Act: -0.0000

Data Index: 970874 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 7.2912. Min Range: -7.2912

Max Act: 5.9887. Min Act: -0.0000

Data Index: 45208 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 7.2912. Min Range: -7.2912

Max Act: 5.9712. Min Act: -0.0000

Data Index: 251430 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 7.2912. Min Range: -7.2912

Max Act: 6.1623. Min Act: -0.0000

Data Index: 261025 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 7.2912. Min Range: -7.2912

Max Act: 6.3410. Min Act: -0.0000

Data Index: 751384 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 7.2912. Min Range: -7.2912

Max Act: 6.1118. Min Act: -0.0000

Data Index: 234526 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 7.2912. Min Range: -7.2912

Max Act: 5.5086. Min Act: -0.0000

Data Index: 726621 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 7.2912. Min Range: -7.2912

Max Act: 5.6934. Min Act: -0.0000

Data Index: 1222438 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 7.2912. Min Range: -7.2912

Max Act: 5.8732. Min Act: -0.0000

Data Index: 911922 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 7.2912. Min Range: -7.2912

Max Act: 5.4204. Min Act: -0.0000

Data Index: 615832 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 7.2912. Min Range: -7.2912

Max Act: 5.7484. Min Act: -0.0000

Data Index: 908248 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 7.2912. Min Range: -7.2912

Max Act: 6.1591. Min Act: -0.0000

Data Index: 343074 (C4 (Web Text))

Max Activating Token Index: 197